Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28502
    Prev
    Next
    INDEX
    Explanations

    function calls or definitions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hhhhhhhh
    -0.70
    mainloop
    -0.63
    mpo
    -0.61
    ス
    -0.61
    Население
    -0.60
    cipar
    -0.60
    ulkner
    -0.60
     nạ
    -0.59
    ervlak
    -0.59
    ceb
    -0.59
    POSITIVE LOGITS
    ());
    1.08
    "");
    1.04
    ]();
    1.03
    "]))
    1.02
    ()).
    1.02
    ']").
    1.00
    ")));
    0.99
    "]).
    0.98
     ")";
    0.98
    ]),
    
    0.97
    Activations Density 0.035%

    No Known Activations